Description
Reproducible when compiled with -Phive-0.13.1, -Phive0.12.0 is OK.
Reproduction steps with hive/console:
scala> loadTestTable("src") scala> sql("SELECT PMOD(key, 10) FROM src LIMIT 1").collect() ... 14/12/08 15:11:31 INFO DAGScheduler: Job 0 failed: runJob at basicOperators.scala:141, took 0.235788 s org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.NullPointerException at org.apache.hadoop.hive.ql.udf.generic.GenericUDFBaseNumeric.initialize(GenericUDFBaseNumeric.java:109) at org.apache.hadoop.hive.ql.udf.generic.GenericUDF.initializeAndFoldConstants(GenericUDF.java:116) at org.apache.spark.sql.hive.HiveGenericUdf.returnInspector$lzycompute(hiveUdfs.scala:156) at org.apache.spark.sql.hive.HiveGenericUdf.returnInspector(hiveUdfs.scala:155) at org.apache.spark.sql.hive.HiveGenericUdf.eval(hiveUdfs.scala:174) at org.apache.spark.sql.catalyst.expressions.Alias.eval(namedExpressions.scala:92) at org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68) at org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$10.next(Iterator.scala:312) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) at scala.collection.AbstractIterator.to(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) at org.apache.spark.sql.execution.Limit$$anonfun$4.apply(basicOperators.scala:141) at org.apache.spark.sql.execution.Limit$$anonfun$4.apply(basicOperators.scala:141) at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314) at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61) at org.apache.spark.scheduler.Task.run(Task.scala:56) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420) at akka.actor.Actor$class.aroundReceive(Actor.scala:465) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516) at akka.actor.ActorCell.invoke(ActorCell.scala:487) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238) at akka.dispatch.Mailbox.run(Mailbox.scala:220) at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393) at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
This issue is introduced in PR #3109, where GenericUDF.initialize was replaced by GenericUDF.initializeAndFoldConstants, which then calls GenericUDFBaseNumeric.initialize in case of PMOD. However, GenericUDFBaseNumeric.initialize needs to access the current SessionState [1], which only exists on the driver side. Thus, when executed on executor side, an NPE is thrown.